voidly

TurkmenistanTM

stable (-4.8pp)

30-day day-by-day shutdown-risk trajectory. Each point is a per-horizon XGBoost prediction (h=1..30) with a 90% conformal band derived from absolute LOCO residuals. Peak risk highlighted.

Peak day
35.1%
d21 · 2026-07-27
Floor day
7.6%
d30 · 2026-08-05
30-day delta
-4.8pp
d30 vs d1 probability

30-day trajectory with 90% conformal band

model trajectory_v1
0%25%50%75%100%d1d7d14d21d30peak d21 35%
mean P(shutdown by day)90% conformal bandpeak day

Drivers (SHAP top 3 from the 7-day model — same features feed all horizons)

day 112.4%
2026-07-07
  • week_of_year-0.024
  • risk_tier-0.014
  • gdelt_conflict_tone_7d+0.010
day 730.5%
2026-07-13
  • week_of_year-0.024
  • risk_tier-0.014
  • gdelt_conflict_tone_7d+0.010
day 1416.4%
2026-07-20
  • week_of_year-0.024
  • risk_tier-0.014
  • gdelt_conflict_tone_7d+0.010
day 307.6%
2026-08-05
  • week_of_year-0.024
  • risk_tier-0.014
  • gdelt_conflict_tone_7d+0.010

Honest caveats

  • Per-horizon XGBoost stacked into a trajectory — not a true joint distribution.
  • Conformal bands are absolute-residual q90 from LOCO predictions on 18 eval countries.
  • Long horizons (h>=14d) have wider effective uncertainty than the conformal q90 suggests; the same lag features feed all horizons.
  • Bands floor at [0,1]; probabilities below 0.05 are at the model's noise floor.
  • SHAP attribution above is from the 7-day point model. The trajectory uses 30 separate per-horizon XGBoost models that share the same feature set; we have not yet computed per-horizon SHAP.

Sample horizons

DayDateP(shutdown)90% interval
d12026-07-0712.4%[0%, 56%]
d72026-07-1330.5%[0%, 95%]
d142026-07-2016.4%[0%, 85%]
d302026-08-057.6%[0%, 86%]
Spotlight countries